Triple
T3381837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Berlin |
E71201
|
entity |
| Predicate | employedApprox |
P803
|
FINISHED |
| Object | about 8000 employees |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: about 8000 employees | Statement: [Air Berlin, employedApprox, about 8000 employees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employedApprox Context triple: [Air Berlin, employedApprox, about 8000 employees]
-
A.
employedApproximately
chosen
Indicates that one entity employs another in a manner where the number, duration, or extent of employment is approximate rather than exact.
-
B.
employedPeople
Indicates that there exists a relationship where people are currently working in jobs or positions, typically under an employer.
-
C.
employedRole
Indicates that an entity holds or performs a specific role or position within an employment or work context.
-
D.
employerIn
Indicates that one entity serves as the employer of another within a specified context, such as a location, organization, or time period.
-
E.
employmentType
Indicates the specific kind or category of employment relationship that exists between an individual and an employer (e.g., full-time, part-time, contract).
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85a8fd9c819095ecedf838d2bf1b |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb5e9af608190bfb228ef99a87bb7 |
completed | March 8, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69ada434bae48190a77ea37f9274ad8f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:14 p.m.